Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to expansions or growth in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "expansion" and related growth concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MET
    -0.69
    akia
    -0.67
    fixed
    -0.64
    ppe
    -0.63
    pee
    -0.62
    rol
    -0.62
    âķIJâķIJ
    -0.62
    «
    -0.62
    oka
    -0.62
    eva
    -0.61
    POSITIVE LOGITS
    ary
    1.11
    ist
    1.10
    ansion
    1.01
    ism
    0.97
    arily
    0.94
    ists
    0.90
    alist
    0.82
    naires
    0.81
    ivist
    0.78
     pains
    0.78
    Act Density 0.062%

    No Known Activations